Abstract: The invention relates to a system and method for automated software testing based on ML. The system comprises a software design module 101 which is configured to provide at least one of business requirement, flow document etc. The requirement parser 102 extracts the actionable items from output of the software design module 101. A ML engine 103 uses supervised ML algorithm to map actionable items with the historic test suites. The test suites and test cases are stored in a NoSQL database. Further, a test design module 104 is configured to create automatic test case design based on ML and assign priorities to the test cases using the parser. A human feedback 105 to the system helps to make the system learns or adjusts the decision making to be more precise.

Abstract: The invention provides a system and method for automated software testing based on Machine Learning (ML). The system automatically picks up results of the software test automation reports from software test automation framework. The report parser parses the failures from the report. A ML engine compares them with the failures that are known or present in the NoSQL database. After the creation of bug ticket in the defect-tracking tool, an automated notification system notifies the stakeholders via email or instant messaging about the status of the respective ticket. A feedback to the system by software test engineer helps to make the system learn or adjust the decision making to be more precise.

Abstract: The invention relates to a system and method for automated software testing based on ML. The system comprises a software design module 101 which is configured to provide at least one of business requirement, flow document etc. The requirement parser 102 extracts the actionable items from output of the software design module 101. A ML engine 103 uses supervised ML algorithm to map actionable items with the historic test suites. The test suites and test cases are stored in a NoSQL database. Further, a test design module 104 is configured to create automatic test case design based on ML and assign priorities to the test cases using the parser. A human feedback 105 to the system helps to make the system learns or adjusts the decision making to be more precise.

Abstract: The invention provides a system and method for automated software testing based on Machine Learning (ML). The system automatically picks up results of the software test automation reports from software test automation framework. The report parser parses the failures from the report. A ML engine compares them with the failures that are known or present in the NoSQL database. After the creation of bug ticket in the defect-tracking tool, an automated notification system notifies the stakeholders via email or instant messaging about the status of the respective ticket. A feedback to the system by software test engineer helps to make the system learn or adjust the decision making to be more precise.